End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: oh_v1-2_only_evol_instruct
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v1-2_only_evol_instruct
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v1-2_only_evol_instruct dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8782
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.8782235980033875,
+    "eval_runtime": 55.3154,
+    "eval_samples_per_second": 11.208,
+    "eval_steps_per_second": 0.181,
+    "total_flos": 115525225021440.0,
+    "train_loss": 0.8865012362383414,
+    "train_runtime": 19124.9166,
+    "train_samples_per_second": 1.847,
+    "train_steps_per_second": 0.004
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.8782235980033875,
+    "eval_runtime": 55.3154,
+    "eval_samples_per_second": 11.208,
+    "eval_steps_per_second": 0.181
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 115525225021440.0,
+    "train_loss": 0.8865012362383414,
+    "train_runtime": 19124.9166,
+    "train_samples_per_second": 1.847,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 1.9236885065896117,
+      "learning_rate": 5e-06,
+      "loss": 1.0498,
+      "step": 10
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.644330845637172,
+      "learning_rate": 5e-06,
+      "loss": 0.9524,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9243873357772827,
+      "eval_runtime": 56.0914,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 0.178,
+      "step": 23
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 1.6104003888156406,
+      "learning_rate": 5e-06,
+      "loss": 0.9035,
+      "step": 30
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 0.9369926663723931,
+      "learning_rate": 5e-06,
+      "loss": 0.8651,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.889980673789978,
+      "eval_runtime": 56.2987,
+      "eval_samples_per_second": 11.013,
+      "eval_steps_per_second": 0.178,
+      "step": 46
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 1.4000968762592165,
+      "learning_rate": 5e-06,
+      "loss": 0.8334,
+      "step": 50
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 1.607971597567641,
+      "learning_rate": 5e-06,
+      "loss": 0.7988,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8782235980033875,
+      "eval_runtime": 56.0783,
+      "eval_samples_per_second": 11.056,
+      "eval_steps_per_second": 0.178,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "step": 69,
+      "total_flos": 115525225021440.0,
+      "train_loss": 0.8865012362383414,
+      "train_runtime": 19124.9166,
+      "train_samples_per_second": 1.847,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 69,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 115525225021440.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}